O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Learning Path: TensorFlow: The Road to TensorFlow Second Edition

Video Description

Discover deep learning and machine learning with Python and TensorFlow

In Detail

It can be hard to get started with machine learning, particularly as new frameworks like TensorFlow start to gain traction across enterprise companies. TensorFlow is an open source software library for numerical computation using data flow graphs. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.

This Learning Path begins by covering everything you need to know about Python. We then move on to understand deep learning as implemented by Python and TensorFlow. Finally, we solve common commercial machine learning problems using TensorFlow.

If you have no prior exposure to one of the most important trends impacting how we do data science in the next few years, this Learning Path will help you get up to speed.

Prerequisites: A firm understanding of Python and the Python ecosystem

Resources: Code downloads and errata:

  • Mastering Python - Second Edition

  • Deep Learning with Python

  • Deep Learning with TensorFlow

  • Machine Learning with TensorFlow

  • PATH PRODUCTS

    This path navigates across the following products (in sequential order):

  • Mastering Python - Second Edition (5h 21m)

  • Deep Learning with Python (1h 45m)

  • Deep Learning with TensorFlow (2h)

  • Machine Learning with TensorFlow (1h 14m)

  • Table of Contents

    1. Chapter 1 : Mastering Python - Second Edition
      1. The Course Overview 00:03:25
      2. Python Basic Syntax and Block Structure 00:11:54
      3. Built-in Data Structures and Comprehensions 00:08:55
      4. First-Class Functions and Classes 00:05:50
      5. Extensive Standard Library 00:05:56
      6. New in Python 3.5 00:06:02
      7. Downloading and Installing Python 00:05:17
      8. Using the Command-Line and the Interactive Shell 00:04:01
      9. Installing Packages with pip 00:03:16
      10. Finding Packages in the Python Package Index 00:04:29
      11. Creating an Empty Package 00:05:50
      12. Adding Modules to the Package 00:05:31
      13. Importing One of the Package's Modules from Another 00:05:26
      14. Adding Static Data Files to the Package 00:02:53
      15. PEP 8 and Writing Readable Code 00:07:51
      16. Using Version Control 00:04:48
      17. Using venv to Create a Stable and Isolated Work Area 00:04:41
      18. Getting the Most Out of docstrings 1: PEP 257 and docutils 00:08:00
      19. Getting the Most Out of docstrings 2: doctest 00:04:04
      20. Making a Package Executable via python -m 00:05:52
      21. Handling Command-Line Arguments with argparse 00:06:22
      22. Interacting with the User 00:04:39
      23. Executing Other Programs with Subprocess 00:09:10
      24. Using Shell Scripts or Batch Files to Run Our Programs 00:03:01
      25. Using concurrent.futures 00:13:53
      26. Using Multiprocessing 00:11:22
      27. Understanding Why This Isn't Like Parallel Processing 00:08:02
      28. Using the asyncio Event Loop and Coroutine Scheduler 00:06:52
      29. Waiting for Data to Become Available 00:03:30
      30. Synchronizing Multiple Tasks 00:06:18
      31. Communicating Across the Network 00:03:45
      32. Using Function Decorators 00:06:45
      33. Function Annotations 00:07:09
      34. Class Decorators 00:05:53
      35. Metaclasses 00:05:35
      36. Context Managers 00:05:52
      37. Descriptors 00:05:38
      38. Understanding the Principles of Unit Testing 00:05:07
      39. Using the unittest Package 00:07:28
      40. Using unittest.mock 00:06:12
      41. Using unittest's Test Discovery 00:04:30
      42. Using Nose for Unified Test Discover and Reporting 00:03:42
      43. What Does Reactive Programming Mean? 00:02:50
      44. Building a Simple Reactive Programming Framework 00:07:22
      45. Using the Reactive Extensions for Python (RxPY) 00:10:22
      46. Microservices and the Advantages of Process Isolation 00:04:13
      47. Building a High-Level Microservice with Flask 00:09:59
      48. Building a Low-Level Microservice with nameko 00:06:25
      49. Advantages and Disadvantages of Compiled Code 00:04:42
      50. Accessing a Dynamic Library Using ctypes 00:07:59
      51. Interfacing with C Code Using Cython 00:12:35
    2. Chapter 2 : Deep Learning with Python
      1. The Course Overview 00:03:52
      2. What Is Deep Learning? 00:04:09
      3. Open Source Libraries for Deep Learning 00:04:31
      4. Deep Learning "Hello World!" Classifying the MNIST Data 00:07:57
      5. Introduction to Backpropagation 00:05:24
      6. Understanding Deep Learning with Theano 00:05:04
      7. Optimizing a Simple Model in Pure Theano 00:07:54
      8. Keras Behind the Scenes 00:05:24
      9. Fully Connected or Dense Layers 00:04:46
      10. Convolutional and Pooling Layers 00:06:40
      11. Large Scale Datasets, ImageNet, and Very Deep Neural Networks 00:05:17
      12. Loading Pre-trained Models with Theano 00:05:16
      13. Reusing Pre-trained Models in New Applications 00:07:22
      14. Theano "for" Loops – the "scan" Module 00:05:18
      15. Recurrent Layers 00:06:28
      16. Recurrent Versus Convolutional Layers 00:03:43
      17. Recurrent Networks –Training a Sentiment Analysis Model for Text 00:06:50
      18. Bonus Challenge – Automatic Image Captioning 00:04:41
      19. Captioning TensorFlow – Google's Machine Learning Library 00:05:15
    3. Chapter 3 : Deep Learning with TensorFlow
      1. The Course Overview 00:03:00
      2. Installing TensorFlow 00:05:34
      3. Simple Computations 00:05:32
      4. Logistic Regression Model Building 00:06:59
      5. Logistic Regression Training 00:04:53
      6. Basic Neural Nets 00:05:17
      7. Single Hidden Layer Model 00:05:06
      8. Single Hidden Layer Explained 00:04:33
      9. Multiple Hidden Layer Model 00:05:22
      10. Multiple Hidden Layer Results 00:04:43
      11. Convolutional Layer Motivation 00:05:04
      12. Convolutional Layer Application 00:06:56
      13. Pooling Layer Motivation 00:03:59
      14. Pooling Layer Application 00:04:18
      15. Deep CNN 00:06:29
      16. Deeper CNN 00:04:08
      17. Wrapping Up Deep CNN 00:04:56
      18. Introducing Recurrent Neural Networks 00:09:03
      19. skflow 00:09:19
      20. RNNs in skflow 00:04:04
      21. Research Evaluation 00:06:56
      22. The Future of TensorFlow 00:04:19
    4. Chapter 4 : Machine Learning with TensorFlow
      1. The Course Overview 00:03:48
      2. Introducing Deep Learning 00:03:59
      3. Installing TensorFlow on Mac OSX 00:03:51
      4. Installation on Windows – Pre-Reqeusite Virtual Machine Setup 00:02:49
      5. Installation on Windows/Linux 00:04:01
      6. The Hand-Written Letters Dataset 00:03:01
      7. Automating Data Preparation 00:03:20
      8. Understanding Matrix Conversions 00:05:34
      9. The Machine Learning Life Cycle 00:01:52
      10. Reviewing Outputs and Results 00:02:51
      11. Getting Started with TensorBoard 00:05:09
      12. TensorBoard Events and Histograms 00:05:22
      13. The Graph Explorer 00:05:09
      14. Our Previous Project on TensorBoard 00:05:02
      15. Fully Connected Neural Networks 00:04:44
      16. Convolutional Neural Networks 00:04:59
      17. Programming a CNN 00:05:02
      18. Using TensorBoard on Our CNN 00:01:58
      19. CNN Versus Fully Connected Network Performance 00:02:08